Table of Contents

Karol Hausman
Master of Science
Technische Universität MünchenDepartment of Computer Science
Informatik 9
Karlstrasse 45 (3rd Floor)
80333 München
Germany
Tel: +49-176-311-97976
Fax: +49-89-289-17757
Office:
Mail: hausmankarol@gmail.com
About
THIS PAGE IS DEPRECATED. PLEASE GO TO:
my new home page.
I started working as a research assistant at the Intelligent Autonomous Systems Group in December 2011 and I am mainly cooperating with Dejan Pangeric, Dipl.-Ing. I am mostly involved in robotics perception, however, I have very broad interests in robotics and machine learning fields. I am currently undertaking Master of Robotics, Cognition and Intelligence at Technical University of Munich.
Before joining the group I obtained my B.Sc. at the Faculty of Mechatronics,Warsaw University of Technology (WUT). Additionally, I have been studying Computer Science at WUT and Philosophy at University of Warsaw. In August 2012 I obtained my Master of Robotics at WUT.
In my research I am concentrating on the applied perception for applications in robotics. More specifically, I am particularly involved in the interactive-perception initiative. As part of my research I use ROS, PCL and OpenCV extensively and I am also contributing to these libraries.
Any additional information about me, including a complete CV, is available upon request.
Fields of Interest
- Intelligent Perception
- Computer Vision
- Machine Learning
- Artificial Intelligence
Interactive Segmentation for Textured Objects
![]() | This paper describes a novel object segmentation approach for autonomous service robots acting in human living environments. The proposed system allows a robot to effectively segment textured objects in cluttered scenes by leveraging its manipulation capabilities. Please refer here for more information. |
Interactive Segmentation for Textureless Objects
![]() | This paper describes a textureless object segmentation approach for autonomous service robots acting in human living environments. The novel approach for textureless objects was evaluated on a set of scenes which consist of various textureless flat (e.g. box-like) and round (e.g. cylinder-like) objects and the combinations thereof. Please refer here for more information. |
Other Projects
Code
I use ROS in my research.These are packages that I am currently contributing to:
- Interactive Perception Library:IPL
- Interactive Segmentation for Textured Objects:www.ros.org/wiki/interactive_segmentation_textured
- Interactive Segmentation for Textureless Objects:www.ros.org/wiki/interactive_segmentation_textureless
- Please find my packages on code.cs.tum.edu server
- Please find more of my code on Sourceforge and Github
Videos
Please have a look at my YouTube channel
Publications
Conference Papers
Tracking-based Interactive Segmentation of Textureless Objects , In IEEE International Conference on Robotics and Automation (ICRA), 2013.(Best Service Robotics Paper Award Finalist) [bib] [pdf] |
Workshop Papers
Segmentation of Cluttered Scenes through Interactive Perception , In ICRA 2012 Workshop on Semantic Perception and Mapping for Knowledge-enabled Service Robotics, 2012. [bib] [pdf] |
Segmentation of Textured and Textureless Objects through Interactive Perception , In RSS Workshop on Robots in Clutter: Manipulation, Perception and Navigation in Human Environments, 2012. [bib] [pdf] |